Papers by Faeze Brahman

Towards Inter-character Relationship-driven Story Generation (2022.emnlp-main)

Challenge:	Pre-trained language models learn harmful biases from their training corpora and may repeat these biase if used for generation.
Approach:	They focus on gender biases associated with the protagonist in model-generated stories and use a commonsense reasoning engine to uncover them.
Outcome:	The proposed model-generated stories are based on a commonsense reasoning engine and are able to uncover gender biases in the protagonist's motivations, attributes, mental states, and implications on others.

Copied to clipboard

Anvesh Rao Vijjini, Faeze Brahman, Snigdha Chaturvedi

Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning (2023.emnlp-main)

Challenge:	Recent story generation methods can generate stories based on open-ended prompts and planners but can neither encode character relationships nor give explicit control over the characters and their relationships.
Approach:	They propose a model that uses relationships as latent variables for story generation and propose 'relationship-driven' story generation.
Outcome:	The proposed model generates stories sentence by sentence with relationships that are more faithful to desired relationships while maintaining the content quality.

Copied to clipboard

Ximing Lu, Faeze Brahman, Peter West, Jaehun Jung, Khyathi Chandu, Abhilasha Ravichander, Prithviraj Ammanabrolu, Liwei Jiang, Sahana Ramnath, Nouha Dziri, Jillian Fisher, Bill Lin, Skyler Hallinan, Lianhui Qin, Xiang Ren, Sean Welleck, Yejin Choi

Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model (2024.naacl-long)

Challenge:	Extreme-scale language models have shown exceptional performance on a variety of language tasks, but the degree of control offered by these models through pure prompting is limited.
Approach:	They propose an inference-time policy adapter which tailors a large base model without fine-tuning it.
Outcome:	The proposed model outperforms baseline methods on five challenging text generation tasks and even over GPT-4.

Copied to clipboard

Jaehun Jung, Peter West, Liwei Jiang, Faeze Brahman, Ximing Lu, Jillian Fisher, Taylor Sorensen, Yejin Choi

IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance (2026.tacl-1)

Challenge:	Impossible Distillation is a framework for paraphrasing and sentence summarization that can be trained from a low-quality teacher model.
Approach:	They propose a framework that distills a high-quality dataset from a low-quality teacher . they hypothesize and verify the paraphrastic proximity intrinsic to pre-trained LMs .
Outcome:	The proposed framework outperforms baseline models on unconstrained paraphrase generation and sentence summarization benchmarks.

Copied to clipboard

Paul Röttger, Musashi Hinck, Valentin Hofmann, Kobi Hackenburg, Valentina Pyatkin, Faeze Brahman, Dirk Hovy

What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations (2023.findings-emnlp)

Challenge:	Large language models are helping millions of users write texts about diverse issues . issue bias is where an LLM tends to present just one perspective on a given issue .
Approach:	They construct a set of 2.49m realistic English-language prompts to measure issue bias in LLM writing assistance using 3.9k templates and 212 political issues from real user interactions.
Outcome:	The proposed model aligns more with US Democrat than Republican voter opinion on a subset of issues.

Copied to clipboard

Kavel Rao, Liwei Jiang, Valentina Pyatkin, Yuling Gu, Niket Tandon, Nouha Dziri, Faeze Brahman, Yejin Choi

Semantic Text Processing

Challenge:	Moral or ethical judgments rely heavily on the contexts in which they occur . a student model that produces defeasible contexts with improved validity, diversity, and defasibility is superior to intermediate student models .
Approach:	a new study uses a student model to provide contextualizations that make an action morally acceptable . the model is based on a dataset of 115K defeasible moral actions rated highly by human annotators .
Outcome:	The proposed model outperforms all intermediate models in a high-quality dataset . the model is based on 1.2M entries of contextualizations and rationales for 115K moral actions .

How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models (2024.findings-emnlp)

Copied to clipboard

Jaeyoung Lee, Ximing Lu, Jack Hessel, Faeze Brahman, Youngjae Yu, Yonatan Bisk, Yejin Choi, Saadia Gabriel

Multimodality

Challenge:	a growing influx of misinformation across news and social media is hampered by outdated foundation model training data.
Approach:	They propose to use large language models to scale up online policing mechanisms . they evaluate foundation model performance without continual updating .
Outcome:	The proposed model can improve performance without continual updating . the proposed model improves on two widely used benchmarks .

Reasoning Up the Instruction Ladder for Controllable Language Models (2026.findings-acl)

Copied to clipboard

Zishuo Zheng, Vidhisha Balachandran, Chan Young Park, Faeze Brahman, Sachin Kumar

NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization (2022.findings-emnlp)

Challenge:	Current models struggle to balance competing directives, causing conflicting instructions.
Approach:	They propose to reframe instruction hierarchy resolution as a reasoning task . they use a training dataset to enable this capability by transferring general reasoning capabilities to instruction prioritization .
Outcome:	The proposed method improves on safety-critical scenarios beyond the training distribution and jailbreaks.

Copied to clipboard

Chao Zhao, Faeze Brahman, Kaiqiang Song, Wenlin Yao, Dian Yu, Snigdha Chaturvedi

ParsiNLU: A Suite of Language Understanding Challenges for Persian (2021.tacl-1)

Challenge:	Existing studies focus on summarizing news documents or structured documents.
Approach:	They propose to use a large-scale narrative summarization dataset to encourage research . they find there is a performance gap between humans and the models on NarraSum .
Outcome:	The proposed dataset shows that humans and state-of-the-art models perform poorly when summarizing a narrative . it contains 122K narratives collected from synopses of movies and TV episodes with diverse genres .

Copied to clipboard

Daniel Khashabi, Arman Cohan, Siamak Shakeri, Pedram Hosseini, Pouya Pezeshkpour, Malihe Alikhani, Moin Aminnaseri, Marzieh Bitaab, Faeze Brahman, Sarik Ghazarian, Mozhdeh Gheini, Arman Kabiri, Rabeeh Karimi Mahabagdi, Omid Memarrast, Ahmadreza Mosallanezhad, Erfan Noury, Shahab Raji, Mohammad Sadegh Rasooli, Sepideh Sadeghi, Erfan Sadeqi Azer, Niloofar Safi Samghabadi, Mahsa Shafaei, Saber Sheybani, Ali Tazarv, Yadollah Yaghoobzadeh

Challenge:	Despite progress in natural language understanding, most progress is concentrated on resource-rich languages like English . despite high-quality benchmarks, there are few available NLU datasets for Persian language .
Approach:	They propose a benchmark for Persian language that includes a range of language understanding tasks . they present their results on monolingual and multilingual pre-trained language models .
Outcome:	The proposed benchmarks compare human performance with monolingual and multilingual models on Persian language with high quality evaluation datasets.

Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization (2024.findings-acl)

Copied to clipboard

Yash Kumar Lal, Li Zhang, Faeze Brahman, Bodhisattwa Prasad Majumder, Peter Clark, Niket Tandon

Challenge:	Using a set of over 200 WikiHow procedures, we test several simple multi-LLM-agent architectures for customization.
Approach:	They propose to use a set of WikiHow procedures to test how-to procedures can be customized by multiple LLMs.
Outcome:	The proposed architecture outperforms an end-to-end LLM in the evaluation set of over 200 WikiHow procedures.

Cue Me In: Content-Inducing Approaches to Interactive Story Generation (2020.aacl-main)

Copied to clipboard

Faeze Brahman, Alexandru Petrusca, Snigdha Chaturvedi

Agent Lumos: Unified and Modular Training for Open-Source Language Agents (2024.acl-long)

Challenge:	Existing methods for automatic story generation focus on one-shot generation, but we focus on interactive story generation.
Approach:	They propose two ways to incorporate user-provided cue phrases into automatic story generation.
Outcome:	The proposed approach produces more topically coherent and personalized stories than baseline methods.

Copied to clipboard

Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, Bill Yuchen Lin

Challenge:	Lumos is a framework for training open-source agents on complex interactive tasks.
Approach:	They propose a framework for training open-source LLM-based agents called Lumos . Lumos features a learnable, unified and modular architecture with a planning module that learns high-level subgoal generation and a grounding module trained to translate these into the actions using various tools in the execution module.
Outcome:	The framework outperforms open-source agents on QA and web tasks.

Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences (2025.findings-emnlp)

Copied to clipboard

Mingqian Zheng, Wenjia Hu, Patrick Zhao, Motahhare Eslami, Jena D. Hwang, Faeze Brahman, Carolyn Rose, Maarten Sap

Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation (2022.findings-emnlp)

Challenge:	Current LLMs are trained to refuse potentially harmful input queries regardless of intent . a study of 480 participants evaluating 3,840 query-response pairs reveals that response strategy largely shapes user experience .
Approach:	They examine how different refusal strategies affect user perceptions across varying motivations . they find partial compliance reduces negative user perception by over 50% to flat-out refusals a 480 participants study .
Outcome:	The study examines the perceptions of LLMs on user intents and their response strategies . it shows that partial compliance reduces negative user perceptions by over 50% to flat refusals .

Copied to clipboard

Faeze Brahman, Baolin Peng, Michel Galley, Sudha Rao, Bill Dolan, Snigdha Chaturvedi, Jianfeng Gao

Modeling Protagonist Emotions for Emotion-Aware Storytelling (2020.emnlp-main)

Challenge:	Large pre-trained language models have enabled open-ended generation frameworks to tackle a variety of tasks beyond data-to-text generation.
Approach:	They propose a new task to generate a factual description about an entity given guiding keys and grounding passages using a dataset.
Outcome:	The proposed model improves factual correctness and recall significantly compared to previous models.

Copied to clipboard

Faeze Brahman, Snigdha Chaturvedi

Challenge:	Cognitive scientists have pinpointed the central role of emotions in storytelling.
Approach:	They propose to use Emotion Supervision and two Emotion-Reinforced models to generate stories that follow the desired emotion arcs for the protagonist.
Outcome:	The proposed models generate stories that follow the desired emotion arcs without sacrificing story quality.

AI-LieDar : Examine the Trade-off Between Utility and Truthfulness in LLM Agents (2025.naacl-long)

Copied to clipboard

Zhe Su, Xuhui Zhou, Sanketh Rangreji, Anubha Kabra, Julia Mendelsohn, Faeze Brahman, Maarten Sap

Challenge:	LieDar is a framework to study how LLM-based agents navigate these scenarios in a multi-turn interactive setting.
Approach:	They propose a framework to study how LLM-based agents navigate these scenarios in an interactive multi-turn setting.
Outcome:	The proposed framework shows that all models are truthful less than 50% of the time, although truthfulness and goal achievement rates vary across models.

REV: Information-Theoretic Evaluation of Free-Text Rationales (2023.acl-long)

Copied to clipboard

Hanjie Chen, Faeze Brahman, Xiang Ren, Yangfeng Ji, Yejin Choi, Swabha Swayamdipta

Is Everything in Order? A Simple Way to Order Sentences (2021.emnlp-main)

Challenge:	Existing metrics for rationale evaluation focus on the association between the rationale and a label, whereas REV is more sensitive to new information in free-text rationales.
Approach:	They propose a metric called REV to quantify the amount of new, label-relevant information in a rationale beyond the information already available in the input or the label.
Outcome:	The proposed metric is consistent with human judgments on rationale evaluations and provides more sensitive measurements of new information in free-text rationales.

Copied to clipboard

Somnath Basu Roy Chowdhury, Faeze Brahman, Snigdha Chaturvedi

Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback (2025.acl-long)

Challenge:	Existing work on sentence ordering has focused on exploiting different categories of features like coreference clues.
Approach:	They propose a sentence ordering task as a conditional text-to-marker generation problem that leverages a pre-trained Transformer-based model to identify a coherent order for a given set of shuffled sentences.
Outcome:	The proposed model performs well across 7 datasets in Perfect Match Ratio and Kendall’s tau.

Copied to clipboard

Lester James Validad Miranda, Yizhong Wang, Yanai Elazar, Sachin Kumar, Valentina Pyatkin, Faeze Brahman, Noah A. Smith, Hannaneh Hajishirzi, Pradeep Dasigi

MacGyver: Are Large Language Models Creative Problem Solvers? (2024.naacl-long)

Challenge:	Learning from human feedback has enabled the alignment of language models (LMs) with human preferences.
Approach:	They propose a Hybrid Preference routER that defers an annotation to either humans or LMs, achieving better annotation quality while reducing the cost of human-only annotation.
Outcome:	The proposed model achieves better annotation quality while reducing the cost of human-only annotation.

Copied to clipboard

Yufei Tian, Abhilasha Ravichander, Lianhui Qin, Ronan Le Bras, Raja Marjieh, Nanyun Peng, Yejin Choi, Thomas Griffiths, Faeze Brahman

UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations (2024.naacl-long)

Challenge:	a new study examines the creative problem-solving capabilities of modern LLMs . it provides insight into the constrained problem- solving capabilities of both humans and AI .
Approach:	They use an automatically generated dataset to compare and contrast LLMs and humans to find out their creative problem-solving abilities.
Outcome:	The proposed dataset compares LLMs and humans in a constrained setting . it shows that humans excel in tasks they are familiar with but struggle with domain-specific knowledge .

Copied to clipboard

Wenting Zhao, Justin Chiu, Jena Hwang, Faeze Brahman, Jack Hessel, Sanjiban Choudhury, Yejin Choi, Xiang Li, Alane Suhr

Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations (2022.emnlp-main)

Challenge:	Existing work evaluating commonsense reasoning focuses on making inferences about common, everyday situations.
Approach:	They propose to use an English language corpus to investigate commonsense reasoning . they characterize performance differences between human explainers and best-performing large language models .
Outcome:	The proposed method reduces the loss rate of human-written explanations on commonsense reasoning compared with the vanilla supervised fine-tuning approach .

Copied to clipboard

Jaehun Jung, Lianhui Qin, Sean Welleck, Faeze Brahman, Chandra Bhagavatula, Ronan Le Bras, Yejin Choi

STEER: Unified Style Transfer with Expert Reinforcement (2023.findings-emnlp)

Challenge:	Pre-trained language models struggle with consistent reasoning, and prompting methods are often noisy and inconsistent.
Approach:	They propose a few-shot inference method inspired by the Socratic way of conversation that generates a tree of explanations that bear logical relations between each other and frames it as a satisfiability problem.
Outcome:	The proposed method achieves 20% better accuracy than state-of-the-art prompting methods and performs competitively with supervised models.

Copied to clipboard

Skyler Hallinan, Faeze Brahman, Ximing Lu, Jaehun Jung, Sean Welleck, Yejin Choi

Challenge:	Experimental results show unified style transfer models outperform the 175B instruction-tuned GPT-3 on overall style transfer quality.
Approach:	They propose a unified style transfer framework that can transfer to multiple target styles from an arbitrary source style.
Outcome:	The proposed method outperforms the 175B instruction-tuned GPT-3 on overall style transfer quality despite being 226 times smaller in size .

Affective and Dynamic Beam Search for Story Generation (2023.findings-emnlp)

Copied to clipboard

Tenghao Huang, Ehsan Qasemi, Bangzheng Li, He Wang, Faeze Brahman, Muhao Chen, Snigdha Chaturvedi

“Let Your Characters Tell Their Story”: A Dataset for Character-Centric Narrative Understanding (2021.findings-emnlp)

Challenge:	AffGen introduces ‘intriguing twists’ in narratives by employing two novel techniques—Dynamic Beam Sizing and Affective Reranking.
Approach:	They propose to use dynamic beam sizing and affective reranking to generate interesting stories using two novel techniques.
Outcome:	The proposed method outperforms baseline models in generating affectively charged and interesting narratives.

Copied to clipboard

Faeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao, Mrinmaya Sachan, Snigdha Chaturvedi

Challenge:	Existing studies on character-centric understanding of narratives focus on understanding the characters in the narrative, but these studies are limited to understanding only certain aspects of characters.
Approach:	They propose a dataset of literary pieces and their summaries paired with descriptions of characters that appear in them that are used to facilitate character-centric narrative understanding.
Outcome:	The proposed dataset includes literary pieces and their summaries paired with descriptions of characters that appear in them.

In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search (2024.emnlp-main)

Copied to clipboard

Huihan Li, Yuting Ning, Zeyi Liao, Siyuan Wang, Xiang Li, Ximing Lu, Wenting Zhao, Faeze Brahman, Yejin Choi, Xiang Ren

Information Retrieval

Challenge:	Logic-Induced-Knowledge-Search (LINK) is a framework for generating factually-correct yet long-tail inferential knowledge.
Approach:	They introduce a framework to obtain factually-correct yet long-tail inferential statements using variable-wise prompting grounded on symbolic rules.
Outcome:	The proposed framework is able to obtain factually-correct yet long-tail inferential statements while ensuring factual correctness.

Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach (2022.findings-naacl)

Copied to clipboard

Chao Zhao, Faeze Brahman, Tenghao Huang, Snigdha Chaturvedi